Fuzzy Sign test for imprecise quantities: A p-value approach

摘要: This paper extends the non-parametric Sign test to case when available observations and underlying hypotheses about population median are imprecise quantities. To do this, by using some elements of possibility theory, we suggest a ranking index among observations. The is applied extend usual concepts classical hypothesis testing problem obtain Sing statistic interval p-value. Comparing p-value nominal significance level, fuzzy constructed providing degrees accept or reject hypotheses. Several numerical examples provided throughout clarify proposed approach. Finally, comprehensive review several well-known approaches given.